Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    expressions of uncertainty or conjecture about information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    guessing that

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     autorytatywna
    -0.66
     AssemblyCompany
    -0.60
     ſta
    -0.57
    bewerken
    -0.55
    сылкі
    -0.54
    ssymb
    -0.54
     Conſ
    -0.51
     ſch
    -0.49
     ſche
    -0.48
     NSCoder
    -0.47
    POSITIVE LOGITS
    umably
    0.54
     probably
    0.52
     vermutlich
    0.52
     prolly
    0.51
     provavelmente
    0.50
    mutlich
    0.50
    Probably
    0.50
     Probably
    0.49
    probably
    0.48
     guessing
    0.47
    Act Density 0.034%

    No Known Activations